| { | |
| "best_metric": 6.792733192443848, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-450", | |
| "epoch": 0.11763321962122103, | |
| "eval_steps": 50, | |
| "global_step": 500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00023526643924244207, | |
| "eval_loss": 6.933060169219971, | |
| "eval_runtime": 3.2084, | |
| "eval_samples_per_second": 557.906, | |
| "eval_steps_per_second": 139.632, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0023526643924244206, | |
| "grad_norm": 0.6924540996551514, | |
| "learning_rate": 4.2800000000000004e-05, | |
| "loss": 6.9289, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.004705328784848841, | |
| "grad_norm": 0.6077510118484497, | |
| "learning_rate": 8.560000000000001e-05, | |
| "loss": 6.9322, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.007057993177273262, | |
| "grad_norm": 0.5621480941772461, | |
| "learning_rate": 0.0001284, | |
| "loss": 6.9184, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.009410657569697682, | |
| "grad_norm": 0.8597236275672913, | |
| "learning_rate": 0.00017120000000000001, | |
| "loss": 6.8977, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.011763321962122103, | |
| "grad_norm": 0.7145811319351196, | |
| "learning_rate": 0.000214, | |
| "loss": 6.8562, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.011763321962122103, | |
| "eval_loss": 6.864169597625732, | |
| "eval_runtime": 3.1888, | |
| "eval_samples_per_second": 561.335, | |
| "eval_steps_per_second": 140.491, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.014115986354546525, | |
| "grad_norm": 0.49429962038993835, | |
| "learning_rate": 0.00021373935337780118, | |
| "loss": 6.8976, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.016468650746970945, | |
| "grad_norm": 0.4391353726387024, | |
| "learning_rate": 0.00021295868335534802, | |
| "loss": 6.8643, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.018821315139395365, | |
| "grad_norm": 0.4785984754562378, | |
| "learning_rate": 0.0002116617932785172, | |
| "loss": 6.8459, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.021173979531819785, | |
| "grad_norm": 0.5224839448928833, | |
| "learning_rate": 0.00020985500146540012, | |
| "loss": 6.8126, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.023526643924244205, | |
| "grad_norm": 0.7273280024528503, | |
| "learning_rate": 0.0002075471104240922, | |
| "loss": 6.8084, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.023526643924244205, | |
| "eval_loss": 6.832787036895752, | |
| "eval_runtime": 3.2348, | |
| "eval_samples_per_second": 553.365, | |
| "eval_steps_per_second": 138.496, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.025879308316668626, | |
| "grad_norm": 0.907507598400116, | |
| "learning_rate": 0.00020474936396775828, | |
| "loss": 6.8848, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.02823197270909305, | |
| "grad_norm": 0.47431233525276184, | |
| "learning_rate": 0.00020147539243590517, | |
| "loss": 6.8506, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.03058463710151747, | |
| "grad_norm": 0.5569249391555786, | |
| "learning_rate": 0.00019774114628873756, | |
| "loss": 6.8298, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.03293730149394189, | |
| "grad_norm": 0.5526637434959412, | |
| "learning_rate": 0.00019356481839811937, | |
| "loss": 6.7974, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.03528996588636631, | |
| "grad_norm": 0.7836293578147888, | |
| "learning_rate": 0.00018896675541373064, | |
| "loss": 6.7893, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.03528996588636631, | |
| "eval_loss": 6.818791389465332, | |
| "eval_runtime": 3.2485, | |
| "eval_samples_per_second": 551.016, | |
| "eval_steps_per_second": 137.908, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.03764263027879073, | |
| "grad_norm": 0.6871911883354187, | |
| "learning_rate": 0.00018396935863623567, | |
| "loss": 6.8675, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.039995294671215154, | |
| "grad_norm": 0.5481328964233398, | |
| "learning_rate": 0.00017859697488039784, | |
| "loss": 6.8491, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.04234795906363957, | |
| "grad_norm": 0.5421447157859802, | |
| "learning_rate": 0.00017287577785984542, | |
| "loss": 6.8076, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.044700623456063994, | |
| "grad_norm": 0.5816627740859985, | |
| "learning_rate": 0.0001668336406713699, | |
| "loss": 6.7903, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.04705328784848841, | |
| "grad_norm": 0.8540289402008057, | |
| "learning_rate": 0.0001605, | |
| "loss": 6.7782, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.04705328784848841, | |
| "eval_loss": 6.80977725982666, | |
| "eval_runtime": 3.211, | |
| "eval_samples_per_second": 557.461, | |
| "eval_steps_per_second": 139.521, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.049405952240912834, | |
| "grad_norm": 0.6835295557975769, | |
| "learning_rate": 0.00015390571270643128, | |
| "loss": 6.8697, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.05175861663333725, | |
| "grad_norm": 0.723054826259613, | |
| "learning_rate": 0.0001470829054955026, | |
| "loss": 6.8365, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.054111281025761675, | |
| "grad_norm": 0.6531696319580078, | |
| "learning_rate": 0.00014006481839811937, | |
| "loss": 6.8019, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.0564639454181861, | |
| "grad_norm": 0.5882543921470642, | |
| "learning_rate": 0.00013288564282916442, | |
| "loss": 6.7801, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.058816609810610515, | |
| "grad_norm": 0.7119730710983276, | |
| "learning_rate": 0.00012558035501036158, | |
| "loss": 6.7837, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.058816609810610515, | |
| "eval_loss": 6.803854465484619, | |
| "eval_runtime": 3.3022, | |
| "eval_samples_per_second": 542.059, | |
| "eval_steps_per_second": 135.666, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.06116927420303494, | |
| "grad_norm": 0.7334095239639282, | |
| "learning_rate": 0.00011818454556963892, | |
| "loss": 6.8623, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.06352193859545936, | |
| "grad_norm": 0.4964336156845093, | |
| "learning_rate": 0.00011073424614716762, | |
| "loss": 6.8151, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.06587460298788378, | |
| "grad_norm": 0.6035408973693848, | |
| "learning_rate": 0.00010326575385283242, | |
| "loss": 6.8015, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.0682272673803082, | |
| "grad_norm": 0.723812460899353, | |
| "learning_rate": 9.58154544303611e-05, | |
| "loss": 6.7626, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.07057993177273263, | |
| "grad_norm": 1.4514328241348267, | |
| "learning_rate": 8.841964498963846e-05, | |
| "loss": 6.7715, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.07057993177273263, | |
| "eval_loss": 6.798593044281006, | |
| "eval_runtime": 3.2084, | |
| "eval_samples_per_second": 557.906, | |
| "eval_steps_per_second": 139.632, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.07293259616515704, | |
| "grad_norm": 0.9387493133544922, | |
| "learning_rate": 8.111435717083556e-05, | |
| "loss": 6.8594, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.07528526055758146, | |
| "grad_norm": 0.4966665506362915, | |
| "learning_rate": 7.393518160188063e-05, | |
| "loss": 6.8124, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.07763792495000588, | |
| "grad_norm": 0.5690203905105591, | |
| "learning_rate": 6.69170945044974e-05, | |
| "loss": 6.7967, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.07999058934243031, | |
| "grad_norm": 0.5846540927886963, | |
| "learning_rate": 6.009428729356871e-05, | |
| "loss": 6.788, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.08234325373485472, | |
| "grad_norm": 0.8786140084266663, | |
| "learning_rate": 5.3500000000000026e-05, | |
| "loss": 6.7735, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.08234325373485472, | |
| "eval_loss": 6.795702934265137, | |
| "eval_runtime": 3.2583, | |
| "eval_samples_per_second": 549.37, | |
| "eval_steps_per_second": 137.496, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.08469591812727914, | |
| "grad_norm": 0.5708802342414856, | |
| "learning_rate": 4.7166359328630106e-05, | |
| "loss": 6.8333, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.08704858251970357, | |
| "grad_norm": 0.5529999136924744, | |
| "learning_rate": 4.112422214015456e-05, | |
| "loss": 6.8258, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.08940124691212799, | |
| "grad_norm": 0.6375375390052795, | |
| "learning_rate": 3.5403025119602206e-05, | |
| "loss": 6.7989, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.0917539113045524, | |
| "grad_norm": 0.974999189376831, | |
| "learning_rate": 3.0030641363764346e-05, | |
| "loss": 6.751, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.09410657569697682, | |
| "grad_norm": 1.1716803312301636, | |
| "learning_rate": 2.5033244586269365e-05, | |
| "loss": 6.7699, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.09410657569697682, | |
| "eval_loss": 6.793699741363525, | |
| "eval_runtime": 3.2263, | |
| "eval_samples_per_second": 554.821, | |
| "eval_steps_per_second": 138.86, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.09645924008940125, | |
| "grad_norm": 0.6257851719856262, | |
| "learning_rate": 2.0435181601880635e-05, | |
| "loss": 6.8415, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.09881190448182567, | |
| "grad_norm": 0.5798721313476562, | |
| "learning_rate": 1.625885371126242e-05, | |
| "loss": 6.825, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.10116456887425009, | |
| "grad_norm": 0.5897112488746643, | |
| "learning_rate": 1.2524607564094813e-05, | |
| "loss": 6.797, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.1035172332666745, | |
| "grad_norm": 0.7111787796020508, | |
| "learning_rate": 9.250636032241695e-06, | |
| "loss": 6.772, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.10586989765909893, | |
| "grad_norm": 1.2426642179489136, | |
| "learning_rate": 6.45288957590781e-06, | |
| "loss": 6.7647, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.10586989765909893, | |
| "eval_loss": 6.792733192443848, | |
| "eval_runtime": 3.2252, | |
| "eval_samples_per_second": 555.008, | |
| "eval_steps_per_second": 138.907, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.10822256205152335, | |
| "grad_norm": 0.5731855630874634, | |
| "learning_rate": 4.144998534599878e-06, | |
| "loss": 6.8432, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.11057522644394777, | |
| "grad_norm": 0.7041200399398804, | |
| "learning_rate": 2.3382067214827915e-06, | |
| "loss": 6.8216, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.1129278908363722, | |
| "grad_norm": 0.7549869418144226, | |
| "learning_rate": 1.0413166446519713e-06, | |
| "loss": 6.7779, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.11528055522879661, | |
| "grad_norm": 0.7202994227409363, | |
| "learning_rate": 2.6064662219881083e-07, | |
| "loss": 6.7666, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.11763321962122103, | |
| "grad_norm": 1.0722975730895996, | |
| "learning_rate": 0.0, | |
| "loss": 6.7527, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.11763321962122103, | |
| "eval_loss": 6.792914867401123, | |
| "eval_runtime": 3.2274, | |
| "eval_samples_per_second": 554.628, | |
| "eval_steps_per_second": 138.812, | |
| "step": 500 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 500, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 3, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 1 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1201410048000.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |